data.vision¶

Vision utilities.

Datasets¶

`datasets.MNIST`([root, train, transform])	MNIST handwritten digits dataset from http://yann.lecun.com/exdb/mnist
`datasets.FashionMNIST`([root, train, transform])	A dataset of Zalando’s article images consisting of fashion products, a drop-in replacement of the original MNIST dataset from https://github.com/zalandoresearch/fashion-mnist
`datasets.CIFAR10`([root, train, transform])	CIFAR10 image classification dataset from https://www.cs.toronto.edu/~kriz/cifar.html
`datasets.CIFAR100`([root, fine_label, train, …])	CIFAR100 image classification dataset from https://www.cs.toronto.edu/~kriz/cifar.html
`datasets.ImageRecordDataset`(filename[, …])	A dataset wrapping over a RecordIO file containing images.
`datasets.ImageFolderDataset`(root[, flag, …])	A dataset for loading image files stored in a folder structure.

Data transformations¶

`transforms.Compose`(transforms)	Sequentially composes multiple transforms.
`transforms.Cast`([dtype])	Cast input to a specific data type
`transforms.ToTensor`()	Converts an image NDArray to a tensor NDArray.
`transforms.Normalize`(mean, std)	Normalize an tensor of shape (C x H x W) with mean and standard deviation.
`transforms.RandomResizedCrop`(size[, scale, …])	Crop the input image with random scale and aspect ratio.
`transforms.CenterCrop`(size[, interpolation])	Crops the image src to the given size by trimming on all four sides and preserving the center of the image.
`transforms.Resize`(size[, keep_ratio, …])	Resize an image to the given size.
`transforms.RandomFlipLeftRight`()	Randomly flip the input image left to right with a probability of 0.5.
`transforms.RandomFlipTopBottom`()	Randomly flip the input image top to bottom with a probability of 0.5.
`transforms.RandomBrightness`(brightness)	Randomly jitters image brightness with a factor chosen from [max(0, 1 - brightness), 1 + brightness].
`transforms.RandomContrast`(contrast)	Randomly jitters image contrast with a factor chosen from [max(0, 1 - contrast), 1 + contrast].
`transforms.RandomSaturation`(saturation)	Randomly jitters image saturation with a factor chosen from [max(0, 1 - saturation), 1 + saturation].
`transforms.RandomHue`(hue)	Randomly jitters image hue with a factor chosen from [max(0, 1 - hue), 1 + hue].
`transforms.RandomColorJitter`([brightness, …])	Randomly jitters the brightness, contrast, saturation, and hue of an image.
`transforms.RandomLighting`(alpha)	Add AlexNet-style PCA-based noise to an image.